List your company

Scientific Discovery on AIME Agent

37.78Step 1 MeanCOAT
33.15234.353535.55536.7565Mar 15, 2026

Evaluation results

MethodLinks
COATBackbone=Grok-4.1-FR2026.0337.7843.3337.7843.3337.7843.3338.8943.33
CausalPlanner (Meta)Backbone=Grok-4.1-FR2026.0334.4436.6735.5636.6736.674036.6740
ShinkaEvolveBackbone=Grok-4.1-FR2026.0333.3333.3334.4436.6734.4436.6734.4436.67
CausalEvolveBackbone=Grok-4.1-FR2026.0333.3336.6738.894038.894038.8940